{"id":"W2092922846","doi":"10.1145/2344416.2344418","title":"Extracting information networks from the blogosphere","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on the Web","topic":"Topic Modeling","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Relationship extraction; Task (project management); Information extraction; Pruning; Blogosphere; Weighting; Cluster analysis; Data mining; Information retrieval; Relation (database); Filter (signal processing); Artificial intelligence; The Internet; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003846414,0.00008478509,0.00005662276,0.00001337613,0.0004170533,0.0001441963,0.001026823,0.00005257174,0.0001252833],"category_scores_gemma":[0.00004402589,0.00004877771,0.00005662393,0.000175734,0.00002000006,0.001152997,0.00001898816,0.0003313798,0.0001647585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002490597,"about_ca_system_score_gemma":0.00002098018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001196607,"about_ca_topic_score_gemma":0.00002662597,"domain_scores_codex":[0.9992846,0.00007768664,0.0001624921,0.00008849049,0.0001672628,0.0002194795],"domain_scores_gemma":[0.9981307,0.0007607645,0.00006545612,0.0009777369,0.00002437677,0.00004092919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008257072,0.0000663904,0.000482148,0.000002411361,0.00006402059,3.407512e-7,0.00571511,0.08021416,0.0001114098,0.0127299,0.001315569,0.8992903],"study_design_scores_gemma":[0.0002655614,0.00001993955,0.002587153,0.00003544041,0.00003520327,0.00001369124,0.001015076,0.9521189,0.0007077263,0.004113502,0.03885143,0.0002364086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01733432,0.0001199854,0.9719747,0.008622486,0.0008162836,0.0001173229,0.000001978971,0.0001186791,0.0008942197],"genre_scores_gemma":[0.9827712,0.00003116964,0.0152243,0.001723508,0.0001623781,0.00002149648,0.000001026699,0.000004361227,0.00006055068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9654369,"threshold_uncertainty_score":0.3207679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02516296794897443,"score_gpt":0.2268239240225655,"score_spread":0.2016609560735911,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}